Event Location: NSH 1109
Bio: David Silver is a PhD candidate at the Robotics Institute, researching robust mobile robot navigation systems. He has a B.S. in Computer Science and a M.S. in Robotics from CMU. Previously, he has worked with the TSLAM and Subterranean Robotics groups at CMU, and the UPI program at NREC. He is currently involved with the CTA program through the FRC.

Abstract: Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are coupled. When traversing rough terrain, this coupling (in the form of a cost function) has a large impact on robot performance, necessitating a robust design. This talk presents the application of imitation learning to his task. Using expert examples of proper navigation behavior, mappings from both online and offline perceptual data to planning costs are learned. Experimental results are presented from the Crusher autonomous navigation platform, demonstrating a benefit to autonomous
performance as well as a decrease in programmer interaction.